“Two Anthropic API updates we rolled out today: – You can now send multiple consecutive user/assistant messages – Added disable_parallel_tool_use to control tool behavior: when enabled, limits Claude to using just one tool instead of multiple tools per query” / X
“”The [model] that I would say is net best is 3.5 Sonnet, I think that’s a consensus opinion” Appreciate the Claude shoutout @amanrsanger, the full episode was a great listen!
“Reminder: 1. LLM’s, transformers…etc not state secrets any longer. 2. Apple not in OpenAI consortium = Gemini or Anthropic or both as partners. 3. If you believe AI is “core tech” then Apple will not let a third-party control their destiny no matter the cost. (See chips as” / X
“After running these additional experiments, we were impressed by a few things: 1) OpenAI o1 models show a consistent improvement over Anthropic and Google models on our long context RAG Benchmark up to 128k tokens. (3/5)” / X
Introducing the Message Batches API \ Anthropic
“I gave these two tweets to Claude and asked it to come up with similar ones. They are surprisingly good, one actually made me laugh.
“2) Despite lower performance than the SOTA OpenAI and Anthropic models, Google Gemini 1.5 models have consistent RAG performance at extreme context lengths of up to 2 million tokens. (4/5)” / X
“Introducing the Message Batches API—a cost-effective way to process vast amounts of queries asynchronously. You can submit batches of up to 10,000 queries at a time. Each batch is processed within 24 hours and costs 50% less than standard API calls.
“First Sam Altman’s piece on a straight path to AGI and now this piece by Anthropic’s CEO on 2 years to powerful AI, I think that any large organization or agency needs to take the possibility of near-term powerful AI seriously They may be wrong or exaggerating, but worth noting
“One use case for contextual retrieval (@AnthropicAI) is creating a better chunking strategy for a slide deck. Each slide of a slide deck is oftentimes part of a larger section and needs to have the right contextual grounding. Adding in contextual summaries allows the user to ask
Leave a Reply